Re: [PATCH 02/14] aoe: kernel thread handles I/O completions for simple locking

[Andrew Morton <akpm@linux-foundation.org>]

On Sat, 25 Aug 2012 10:39:46 -0400
Ed Cashin <ecashin@coraid.com> wrote:

> +static int
> +kthread(void *vp)
> +{
> +	struct ktstate *k;
> +	DECLARE_WAITQUEUE(wait, current);
> +	int more;
> +
> +	k = vp;
> +	current->flags |= PF_NOFREEZE;
> +	set_user_nice(current, -10);
> +	complete(&k->rendez);	/* tell spawner we're running */
> +	do {
> +		spin_lock_irq(k->lock);
> +		more = k->fn();
> +		if (!more) {
> +			add_wait_queue(k->waitq, &wait);
> +			__set_current_state(TASK_INTERRUPTIBLE);
> +		}
> +		spin_unlock_irq(k->lock);
> +		if (!more) {
> +			schedule();
> +			remove_wait_queue(k->waitq, &wait);
> +		} else
> +			cond_resched();
> +	} while (!kthread_should_stop());
> +	complete(&k->rendez);	/* tell spawner we're stopping */
> +	return 0;
> +}
> +
> +static void
> +aoe_ktstop(struct ktstate *k)
> +{
> +	kthread_stop(k->task);
> +	wait_for_completion(&k->rendez);
> +}
> +
> +static int
> +aoe_ktstart(struct ktstate *k)
> +{
> +	struct task_struct *task;
> +
> +	init_completion(&k->rendez);
> +	task = kthread_run(kthread, k, k->name);
> +	if (task == NULL || IS_ERR(task))
> +		return -ENOMEM;
> +	k->task = task;
> +	wait_for_completion(&k->rendez); /* allow kthread to start */
> +	init_completion(&k->rendez);	/* for waiting for exit later */
> +	return 0;
> +}

It's a pretty unlikely thing, but I wonder if there's a way in which
aoe_ktstart() can run that second init_completion() _after_ kthread()
has run its second complete().  ie: someone runs aoe_ktstop()
super-early.  If that can happen, the later wait_for_completion() hangs
up.